Automated Large-scale CVRP Solver Design via LLM-assisted Flexible MCTS

TL;DR

This paper introduces LaF-MCTS, an LLM-assisted framework that automates the design of large-scale CVRP solvers by hierarchical decision-making and semantic pruning, outperforming existing methods.

Contribution

It presents a novel hierarchical framework combining LLMs with MCTS, enabling automated, high-performance CVRP solver design for large instances.

Findings

LaF-MCTS outperforms state-of-the-art CVRP solvers on CVRPLib.

Semantic pruning and branch regrowth improve search efficiency and diversity.

Automated solver design reduces reliance on expert knowledge and manual tuning.

Abstract

Solving large-scale CVRP (LSCVRP) with hundreds to thousands of nodes remains difficult for even state-of-the-art solvers. Divide-and-conquer can scale by decomposing the instance into size-reduced subproblems, but designing decomposition logic and configuring sub-solvers is highly expertise- and labor-intensive. Large Language Models (LLMs) have emerged as promising tools for automated algorithm design. However, existing LLM-driven approaches struggle with LSCVRP primarily due to the difficulty in generating sophisticated search strategies within a limited context window. To bridge this gap, we propose the LLM-assisted Flexible Monte Carlo Tree Search (LaF-MCTS), a novel framework that automates the design of high-performance LSCVRP solvers. We develop a three-tier decision hierarchy to enable incremental design of decomposition policies and sub-solvers for LSCVRP. To enable efficient search within the algorithmic hypothesis space, we introduce semantic pruning to eliminate semantically and structurally redundant codes, and branch regrowth to regenerate codes and preserve diversity. Extensive experiments on CVRPLib demonstrate that LaF-MCTS autonomously composes and optimizes decomposition-enhanced solvers that surpasses various state-of-the-art CVRP solvers.